telemetry-analyzer

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides Python scripts that execute shell commands to interact with the orchestrate CLI for environment activation and server management. These are standard operations for the IBM watsonx Orchestrate platform.
  • [EXTERNAL_DOWNLOADS]: The skill instructions and README guide the user to install the ibm-watsonx-orchestrate package via pip and fetch telemetry data from IBM-owned API endpoints (/v1/agentops-v3/traces). These resources are from a well-known service and are necessary for the skill's primary function.
  • [DATA_EXPOSURE]: The skill reads telemetry trace data which may contain conversational inputs/outputs. This data is stored locally in a data/ directory for analysis purposes. No evidence of unauthorized exfiltration to third-party domains was detected; network calls target official IBM instance URLs.
  • [SAFE]: The Python scripts (export_traces_adk.py, export_traces_agentops_v3.py, etc.) implement standard API client logic with error handling, rate-limiting retries, and local file I/O for telemetry analysis. The use of .env files for configuration follows security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 10:33 AM
Security Audit — agent-trust-hub — telemetry-analyzer